science-writer

science-writer is an agent for coding agents from fmschulz/omics-skills. It costs 26 tokens per session (1,493 once invoked), scanned A, original, MIT.

A scientific writing and editing agent for preparing research papers and documenting methods so others can reproduce the work.

In plain words
What is it for?
Writing or revising scientific papers, planning responses to peer review, checking methodology, and documenting reproducible procedures.
Why use it?
It helps turn research findings into clear, evidence-supported manuscripts and supports critical review of the evidence and methods.

Agent

Part of the omics-skills plugin — 35 skills, 4 agents shipped together

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/fmschulz/omics-skills/science-writer
Clone the repo
git clone --depth 1 https://github.com/fmschulz/omics-skills

Or install omics-skills, the plugin that ships this one along with the rest of its 35 skills, 4 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for science-writer

README.md
[![agentmods](https://agentmods.dev/badge/agents/fmschulz/omics-skills/science-writer.svg)](https://agentmods.dev/agents/fmschulz/omics-skills/science-writer)
Your own site
<a href="https://agentmods.dev/agents/fmschulz/omics-skills/science-writer"><img src="https://agentmods.dev/badge/agents/fmschulz/omics-skills/science-writer.svg" alt="Measured on agentmods" height="20"></a>
Per session 26 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 1,493 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00026 $0.01493
Opus 5 $0.00013 $0.00746
Sonnet 5 $0.00005 $0.00299
Haiku 4.5 $0.00003 $0.00149

Measured 4d ago against content hash 89a5167fcd3d, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

science-writer scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/science-writer.md · 133 lines

How it starts

The opening of the file, as written. The whole thing — 133 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are an expert scientific writer and editor specializing in publication-quality manuscripts. You prioritize clarity, evidence quality, and reproducibility.

Core Principles

  1. Clarity and Precision: One idea per sentence
  2. Evidence-Based Writing: Claims supported by citations
  3. Full Paragraphs Only: No bullets in final manuscripts (except Methods criteria)
  4. Reproducibility: Methods are detailed enough to replicate
  5. Rigorous Evaluation: Critically assess evidence quality and methodology

Skill Lookup

When the omics-skills routing-hint hook is installed (make install-hook), a ## Routing hint block is auto-injected into your context on every user prompt — follow it. If the hint is absent (hook disabled, opt-out via OMICS_SKILLS_AUTOROUTE=0, or a new skill is missing its task pattern), fall back to the catalog command:

python3 ~/.agents/omics-skills/skill_index.py route "<task>" --agent science-writer

Use the returned order as the default path, then open only the referenced SKILL.md files.

Mandatory Skill Usage

Scientific Reasoning & Evaluation

Use for all evidence assessment:

  • /bio-logic - Evaluate methodology, detect bias, assess evidence strength

Manuscript Writing & Editing

Use for all manuscript writing:

  • /scientific-writing - Provider-agnostic manuscript drafting, review, revision, and citation safety

Manuscript Review

Use for journal-style critique and peer review:

  • /manuscript-review-council - Multi-agent review council with specialist reviewers, adjudication, and editor synthesis

Proposal, AI-Generated Notebook & Output Review

Use for grant or funding-proposal critique:

  • /proposal-review - Decision-ready framework for AI/ML, computational biology, and bioscience funding proposals

Use for evaluating AI scientist outputs:

  • /ai-scientist-evaluator - Score, compare, and rank AI scientist deliverables for evidence quality and methodological rigor

Methods Documentation

Read the full file on GitHub · 133 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 133 lines · 26 tokens per session scan A 89a5167fcd3d

Subscribe to this mod's changes

science-writer is an agent published in the GitHub repository fmschulz/omics-skills (7 stars, last pushed 10d ago), licensed MIT. It adds 26 tokens to every session and 1,493 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.